I asked a local instance of Qwen3.5 122b: "American indie rock/pop band that formed in Ann Arbor, Michigan, in 2001 best known for their eclectic musical style, whimsical lyrics, and distinctive visual aesthetic involving matching colored ties and hats?"

Got this back "The band you are describing is Tally Hall.

Formed by friends at the University of Michigan, they became well-known in the mid-2000s internet era for their songs like "Good Day" and "Rooftops," as well as their signature look where each member wore a suit with a tie and fedora in a specific color (Red, Blue, Yellow, Green, and Black/White)."

Update: The gpt-oss-120b also got it correct on my prompt version. Update 1: Llama 3.1 70B gets it right as well. Update 2: Deepseek V4 Flash gets it right. Update 3: Glm 4.5 Air gets it right as well

Can't seem to get any smaller models to get it.

So seems it could be an issue of data points on which the model can latch onto, the more the merrier, as they say. When asked the "What was that weird band from michigan from the 2000s that wore coloured ties" was not able to get it right.

There's a shockingly unfathomable level of data compression that these local LLMs are able to remember in an encyclopedic way, so many obscure little things.